© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 54226
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arsers
    -0.24
     apologise
    -0.24
    ä¸Ĭ游
    -0.23
     âĶľ
    -0.22
    ä¿Ł
    -0.22
    éĵ¬
    -0.21
    å°ıé¢Ŀ
    -0.20
    oble
    -0.20
    outers
    -0.20
    æī¾äºĨ
    -0.20
    POSITIVE LOGITS
    ÑĢÑĥÑĩ
    0.25
    inkel
    0.25
    iale
    0.24
    iales
    0.23
     Stein
    0.23
    åħ¥åľº
    0.23
    ilee
    0.22
    æĢ§
    0.22
    stein
    0.22
    iaux
    0.21
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.